{"id":"W2048680608","doi":"10.1136/jech-2012-200971","title":"Predictive risk algorithms in a population setting: an overview","year":2012,"lang":"en","type":"article","venue":"Journal of Epidemiology & Community Health","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":51,"is_retracted":false,"has_abstract":true,"ca_institutions":"Public Health Ontario; York University; Ottawa Hospital; Bruyère; University of Ottawa; University of Toronto; Institute for Clinical Evaluative Sciences; Statistics Canada","funders":"Canadian Institutes of Health Research; Health Canada; Canada Research Chairs; Public Health Agency of Canada","keywords":"Medicine; Population; Risk assessment; Population health; Algorithm; Multivariable calculus; Predictive analytics; Machine learning; Risk analysis (engineering); Computer science; Environmental health","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05175742,0.0001786148,0.0008695096,0.0003677407,0.0004987514,0.00001221905,0.001218832,0.0001856504,0.000008282229],"category_scores_gemma":[0.01055293,0.0001542918,0.0001206397,0.0004244422,0.00005824003,0.001050524,0.0002937942,0.004150075,0.00000437806],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006726352,"about_ca_system_score_gemma":0.0003604348,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03476566,"about_ca_topic_score_gemma":0.002773613,"domain_scores_codex":[0.9617575,0.03537593,0.00172387,0.0001748234,0.0002117257,0.000756136],"domain_scores_gemma":[0.9889874,0.006505772,0.002643604,0.001071668,0.0001841708,0.0006074128],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001719009,0.0002143473,0.9199932,0.00008162604,0.0000126735,0.000001144309,0.00420503,0.001572132,2.580586e-7,0.005332008,0.0002511295,0.06831931],"study_design_scores_gemma":[0.0003084155,0.001055964,0.9411344,0.0002063972,0.000005130955,0.0001424064,0.0002125911,0.04270669,2.225591e-7,0.01281886,0.001314735,0.00009418467],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7863681,0.01949463,0.1706363,0.02138038,0.001476236,0.0003983862,0.00001156278,0.00009642798,0.0001379404],"genre_scores_gemma":[0.859875,0.002012761,0.1330994,0.004677211,0.0003057217,0.000003777775,0.00001163942,0.00001196173,0.00000252037],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07350689,"threshold_uncertainty_score":0.9981474,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1735464016432476,"score_gpt":0.467665008228342,"score_spread":0.2941186065850945,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}